© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 90907
    Prev
    Next
    INDEX
    Explanations

    inference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    δος
    0.54
    ্ড
    0.49
    灰
    0.47
     голов
    0.46
    }";
    0.46
    模糊
    0.45
    燙
    0.45
     fouled
    0.44
     Grey
    0.44
     Ска
    0.44
    POSITIVE LOGITS
    ilipp
    0.55
    ie
    0.48
    TEC
    0.46
     คอม
    0.45
    aison
    0.45
    uin
    0.45
    ierte
    0.44
    elow
    0.44
    唃
    0.43
    audio
    0.43
    Activations Density 0.001%

    No Known Activations